{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IEWZIN3AQCQORDYPVULJVPT36H","short_pith_number":"pith:IEWZIN3A","canonical_record":{"source":{"id":"1705.08245","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-23T13:36:00Z","cross_cats_sorted":[],"title_canon_sha256":"26e873a79e9fc805e82251fdd7a9c74302ac11596aaab740d9114cfbdbdf45ba","abstract_canon_sha256":"4ddbfd9d7ec44bfb9e51f5a6f6dcbd80a6b8c098d76af860e9ac4974281b5917"},"schema_version":"1.0"},"canonical_sha256":"412d94376080a0e88f0fad169abe7bf1e5370cc43baf872fc872bde51df874f1","source":{"kind":"arxiv","id":"1705.08245","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08245","created_at":"2026-05-18T00:43:34Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08245v2","created_at":"2026-05-18T00:43:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08245","created_at":"2026-05-18T00:43:34Z"},{"alias_kind":"pith_short_12","alias_value":"IEWZIN3AQCQO","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IEWZIN3AQCQORDYP","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IEWZIN3A","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IEWZIN3AQCQORDYPVULJVPT36H","target":"record","payload":{"canonical_record":{"source":{"id":"1705.08245","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-23T13:36:00Z","cross_cats_sorted":[],"title_canon_sha256":"26e873a79e9fc805e82251fdd7a9c74302ac11596aaab740d9114cfbdbdf45ba","abstract_canon_sha256":"4ddbfd9d7ec44bfb9e51f5a6f6dcbd80a6b8c098d76af860e9ac4974281b5917"},"schema_version":"1.0"},"canonical_sha256":"412d94376080a0e88f0fad169abe7bf1e5370cc43baf872fc872bde51df874f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:34.798935Z","signature_b64":"b7lF9d89bFwQqre71SwBKmU2kHr1ri29U61powZ9j8WHTHQJnve775uodVlNKg+jNwACuk45SCMTPjVEMpu2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"412d94376080a0e88f0fad169abe7bf1e5370cc43baf872fc872bde51df874f1","last_reissued_at":"2026-05-18T00:43:34.798576Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:34.798576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.08245","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:43:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YGGGUCYwpHJLVwJdN5PCyQd9knYkCpzMb0sVsY02ERrZEYAxnxyw/muQTJ5zclo3l6muRyYTJccwMJCV6L5ZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:07:47.511457Z"},"content_sha256":"929758a4d88038b4daca14edb8b1fc0797c1f54bbe633569824f814ef6294f21","schema_version":"1.0","event_id":"sha256:929758a4d88038b4daca14edb8b1fc0797c1f54bbe633569824f814ef6294f21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IEWZIN3AQCQORDYPVULJVPT36H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhanced Experience Replay Generation for Efficient Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Martha Vlachou-Konchylaki, Tobias Ley, Vincent Huang, Wenfeng Hu","submitted_at":"2017-05-23T13:36:00Z","abstract_excerpt":"Applying deep reinforcement learning (RL) on real systems suffers from slow data sampling. We propose an enhanced generative adversarial network (EGAN) to initialize an RL agent in order to achieve faster learning. The EGAN utilizes the relation between states and actions to enhance the quality of data samples generated by a GAN. Pre-training the agent with the EGAN shows a steeper learning curve with a 20% improvement of training time in the beginning of learning, compared to no pre-training, and an improvement compared to training with GAN by about 5% with smaller variations. For real time s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08245","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:43:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l1Ujk0nhG29hCu5oNtFksgWyRq+p7+h0jzvhKj4gsfxvKZzehcgFj8EqWTQoc0prgI7wnJ8NUXAJUDLygbQ4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:07:47.512148Z"},"content_sha256":"7e923e495a8fcb5b65ffee1e48b2ed23d4485fa6ccbeae7eff1f4420992b73b9","schema_version":"1.0","event_id":"sha256:7e923e495a8fcb5b65ffee1e48b2ed23d4485fa6ccbeae7eff1f4420992b73b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEWZIN3AQCQORDYPVULJVPT36H/bundle.json","state_url":"https://pith.science/pith/IEWZIN3AQCQORDYPVULJVPT36H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEWZIN3AQCQORDYPVULJVPT36H/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-11T22:07:47Z","links":{"resolver":"https://pith.science/pith/IEWZIN3AQCQORDYPVULJVPT36H","bundle":"https://pith.science/pith/IEWZIN3AQCQORDYPVULJVPT36H/bundle.json","state":"https://pith.science/pith/IEWZIN3AQCQORDYPVULJVPT36H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEWZIN3AQCQORDYPVULJVPT36H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IEWZIN3AQCQORDYPVULJVPT36H","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4ddbfd9d7ec44bfb9e51f5a6f6dcbd80a6b8c098d76af860e9ac4974281b5917","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-23T13:36:00Z","title_canon_sha256":"26e873a79e9fc805e82251fdd7a9c74302ac11596aaab740d9114cfbdbdf45ba"},"schema_version":"1.0","source":{"id":"1705.08245","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08245","created_at":"2026-05-18T00:43:34Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08245v2","created_at":"2026-05-18T00:43:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08245","created_at":"2026-05-18T00:43:34Z"},{"alias_kind":"pith_short_12","alias_value":"IEWZIN3AQCQO","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IEWZIN3AQCQORDYP","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IEWZIN3A","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:7e923e495a8fcb5b65ffee1e48b2ed23d4485fa6ccbeae7eff1f4420992b73b9","target":"graph","created_at":"2026-05-18T00:43:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Applying deep reinforcement learning (RL) on real systems suffers from slow data sampling. We propose an enhanced generative adversarial network (EGAN) to initialize an RL agent in order to achieve faster learning. The EGAN utilizes the relation between states and actions to enhance the quality of data samples generated by a GAN. Pre-training the agent with the EGAN shows a steeper learning curve with a 20% improvement of training time in the beginning of learning, compared to no pre-training, and an improvement compared to training with GAN by about 5% with smaller variations. For real time s","authors_text":"Martha Vlachou-Konchylaki, Tobias Ley, Vincent Huang, Wenfeng Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-23T13:36:00Z","title":"Enhanced Experience Replay Generation for Efficient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08245","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:929758a4d88038b4daca14edb8b1fc0797c1f54bbe633569824f814ef6294f21","target":"record","created_at":"2026-05-18T00:43:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4ddbfd9d7ec44bfb9e51f5a6f6dcbd80a6b8c098d76af860e9ac4974281b5917","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-23T13:36:00Z","title_canon_sha256":"26e873a79e9fc805e82251fdd7a9c74302ac11596aaab740d9114cfbdbdf45ba"},"schema_version":"1.0","source":{"id":"1705.08245","kind":"arxiv","version":2}},"canonical_sha256":"412d94376080a0e88f0fad169abe7bf1e5370cc43baf872fc872bde51df874f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"412d94376080a0e88f0fad169abe7bf1e5370cc43baf872fc872bde51df874f1","first_computed_at":"2026-05-18T00:43:34.798576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:34.798576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b7lF9d89bFwQqre71SwBKmU2kHr1ri29U61powZ9j8WHTHQJnve775uodVlNKg+jNwACuk45SCMTPjVEMpu2Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:34.798935Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.08245","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:929758a4d88038b4daca14edb8b1fc0797c1f54bbe633569824f814ef6294f21","sha256:7e923e495a8fcb5b65ffee1e48b2ed23d4485fa6ccbeae7eff1f4420992b73b9"],"state_sha256":"c585e486845102367f1e46ceb35a41b952faf5a4d7fbe55a1371c3988728081c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VcATj0y78dwnME6xdtaOcRhOdrrlsdXwdDpi8SyfMVx0Yra0yKP1e8oUG0ySuU+HGR44Cw4BsxrJl4O5AP8cDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T22:07:47.516281Z","bundle_sha256":"2791195d1b1571a18e1e8458609f1f87237af226e8a8d7c987343c87b718f83e"}}